© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7177
    Prev
    Next
    INDEX
    Explanations

    toss, tossing, tossed, discard

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tek
    -0.10
    aul
    -0.09
    oader
    -0.09
    arity
    -0.09
    ONSE
    -0.09
    çªŁ
    -0.09
    æĺ¼
    -0.09
    å¾Īæ¸ħæ¥ļ
    -0.09
    ëĿ¼ëıĦ
    -0.09
    ä¸ĢæŶ
    -0.09
    POSITIVE LOGITS
    ering
    0.10
    ellaneous
    0.10
    à¸Ĺาà¸ĩ
    0.10
    engers
    0.09
    ible
    0.09
    ables
    0.08
    ä¸įå®ļ
    0.08
    yı
    0.08
    abled
    0.08
     Ars
    0.08
    Activations Density 0.004%

    No Known Activations